Scores over time

Best recorded score per model; higher is better. The line follows the running best. Evaluation contexts can differ.

Average accuracy scores over timeOne point per model's best recorded score, dated by reported date or model release date. A line shows the running best. The data table below contains every plotted point.93.187.62026-04-162026-10-07Claude Opus 4.7: 89.9% · Reported 2026-04-16Claude Sonnet 5: 89.3% · Reported 2026-06-30Claude Opus 5: 92.1% · Reported 2026-07-24Claude Fable 5.1: 93.0% · Reported 2026-09-01Claude Opus 5.5: 93.1% · Reported 2026-09-22Claude Sonnet 5.5: 91.6% · Reported 2026-09-28Claude Haiku 5.5: 87.6% · Reported 2026-10-07
Data table
Scores plotted over time
ModelDateScore
Claude Opus 4.7 (Reported)89.9%
Claude Sonnet 5 (Reported)89.3%
Claude Opus 5 (Reported)92.1%
Claude Fable 5.1 (Reported)93.0%
Claude Opus 5.5 (Reported)93.1%
Claude Sonnet 5.5 (Reported)91.6%
Claude Haiku 5.5 (Reported)87.6%

Results

7 results

Multi-task Indic Language Understanding Benchmark Original results
ProviderModelScoreSourceRegistry No.
AnthropicClaude Haiku 5.5 (max)87.6%anthropic.com for Claude Haiku 5.5 (max) on Multi-task Indic Language Understanding Benchmark Original (opens in a new tab)Archived copy (opens in a new tab)Average accuracyReported System cardAnthropicSelf-reportedRecord for Claude Haiku 5.5 on Multi-task Indic Language Understanding Benchmark Original20018
AnthropicClaude Sonnet 5.5 (max)91.6%anthropic.com for Claude Sonnet 5.5 (max) on Multi-task Indic Language Understanding Benchmark Original (opens in a new tab)Average accuracyReported System cardAnthropicSelf-reportedRecord for Claude Sonnet 5.5 on Multi-task Indic Language Understanding Benchmark Original20016
AnthropicClaude Opus 5.5 (max)93.1%www-cdn.anthropic.com for Claude Opus 5.5 (max) on Multi-task Indic Language Understanding Benchmark Original (opens in a new tab)Average accuracyReported System cardAnthropicSelf-reportedRecord for Claude Opus 5.5 on Multi-task Indic Language Understanding Benchmark Original20015
AnthropicClaude Fable 5.1 (max)93.0%www-cdn.anthropic.com for Claude Fable 5.1 (max) on Multi-task Indic Language Understanding Benchmark Original (opens in a new tab)Average accuracyReported System cardAnthropicSelf-reportedRecord for Claude Fable 5.1 on Multi-task Indic Language Understanding Benchmark Original20004
AnthropicClaude Opus 5 (max)92.1%www-cdn.anthropic.com for Claude Opus 5 (max) on Multi-task Indic Language Understanding Benchmark Original (opens in a new tab)Average accuracyReported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on Multi-task Indic Language Understanding Benchmark Original20014
AnthropicClaude Sonnet 5 (max)89.3%www-cdn.anthropic.com for Claude Sonnet 5 (max) on Multi-task Indic Language Understanding Benchmark Original (opens in a new tab)Average accuracyReported System cardAnthropicSelf-reportedRecord for Claude Sonnet 5 on Multi-task Indic Language Understanding Benchmark Original20013
AnthropicClaude Opus 4.7 (adaptive thinking)89.9%www-cdn.anthropic.com for Claude Opus 4.7 (adaptive thinking) on Multi-task Indic Language Understanding Benchmark Original (opens in a new tab)Average accuracyReported System cardAnthropicSelf-reportedRecord for Claude Opus 4.7 on Multi-task Indic Language Understanding Benchmark Original20010